© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7346
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éļĪ
    -0.30
    饯
    -0.26
    itia
    -0.26
    åīįæıIJ
    -0.25
    æĴµ
    -0.24
    \Column
    -0.24
     Ala
    -0.23
    æł·æľ¬
    -0.23
    é³ī
    -0.23
    æł·åĵģ
    -0.23
    POSITIVE LOGITS
     Sob
    0.26
    åľ¨åħ¨åĽ½
    0.25
    -west
    0.25
    æ£īèĬ±
    0.25
    opa
    0.25
    ç¼Ī
    0.24
    éĶ¦ç»£
    0.24
    çľ¼çľĭ
    0.24
    ager
    0.24
     projectName
    0.24
    Activations Density 0.012%

    No Known Activations